Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130849
    Prev
    Next
    INDEX
    Explanations

    94 and 944

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arul
    -0.10
    .Style
    -0.09
     않았다
    -0.09
    ഖ്യാപ
    -0.08
    ungkinan
    -0.08
     Karachi
    -0.08
     스타일
    -0.08
    uyu
    -0.08
     postura
    -0.08
     KAR
    -0.08
    POSITIVE LOGITS
    94
    0.10
    944
    0.09
    month
    0.08
    appa
    0.07
    imeline
    0.07
     week
    0.07
     iso
    0.06
     ganze
    0.06
     ٻ
    0.06
     Send
    0.06
    Activations Density 0.001%

    No Known Activations